Konstantinos Papaioannou – PhD Student, Systems for ML (LLM Inference Serving)

Bio

I am a final-year Computer Science Ph.D. student at IMDEA Software Institute, advised by Thaleia Dimitra Doudali, working on Systems for Machine Learning. My research focuses on making inference serving efficient for multimodal LLMs and other foundation models, through request scheduling, KV cache management, and pipeline-aware serving.

Previously, I received my Diploma in Electrical and Computer Engineering from the National Technical University of Athens. During my last year, I completed my Diploma thesis on "Optimizing ML Workflows by Integrating a Feature Store into Kubeflow", supervised by Nectarios Koziris and Vangelis Koukis.

💼 I am looking for industry research and engineering roles starting in October 2027.

Research

ML Inference Serving Systems
Multimodal Inference Scheduling and KV Cache Management
Pipeline-Aware Serving for Any-to-Any Models

Education

Oct 2022 - Sept 2027 (exp.)
PhD in CS
IMDEA Software Institute
2017 - 2022
MEng in ECE
National Technical University of Athens

Experience

Research Intern @ IBM

Jun 2026 - Sept 2026

Worked with the Next Generation Systems team on serving geospatial foundation models at scale, using vLLM and llm-d.

Thesis Intern @ Arrikto

Oct 2021 - Sept 2022

Transformed Feast, an open-source feature store, into a cloud-native client-server system integrated with Kubeflow on Kubernetes.

Publications

2026
- Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference
  Konstantinos Papaioannou, Thaleia Dimitra Doudali
  In Proceedings of the 2026 SIGOPS Annual Technical Conference (ATC ’26)
- CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-Tenant LLM Serving Systems
  Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri, Thaleia Dimitra Doudali
  In Proceedings of the 76th International Middleware Conference (Middleware ’26)
- Dealing with the Elephant in the KV Cache: Video Frame Sampling for Multimodal LLM Inference
  Konstantinos Papaioannou, Thaleia Dimitra Doudali
  In Proceedings of the 6th Workshop on Machine Learning and Systems (EuroMLSys ’26)
  In conjunction with the 2026 European Conference on Computer Systems (EuroSys ’26)
2024
- The Importance of Workload Choice in Evaluating LLM Inference Systems
  Konstantinos Papaioannou, Thaleia Dimitra Doudali
  In Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys ’24)
  In conjunction with the 2024 European Conference on Computer Systems (EuroSys ’24)
2023
- Is Machine Learning Necessary for Cloud Resource Usage Forecasting?
  Georgia Christofidi, Konstantinos Papaioannou, Thaleia Dimitra Doudali
  In Proceedings of the 14th Symposium of Cloud Computing (SoCC ’23)
- Toward Pattern-based Model Selection for Cloud Resource Forecasting
  Georgia Christofidi, Konstantinos Papaioannou, Thaleia Dimitra Doudali
  In Proceedings of the 3rd Workshop on Machine Learning and Systems (EuroMLSys ’23)
  In conjunction with the 2023 European Conference on Computer Systems (EuroSys ’23)

Service

CAIS 2026
Artifact Evaluation Committee (AEC)
EuroSys 2026
Shadow Program Committee (Shadow PC)
Artifact Evaluation Committee (AEC)
EuroSys 2025
Shadow Program Committee (Shadow PC)
ATC 2024
Artifact Evaluation Committee (AEC)
OSDI 2024
Artifact Evaluation Committee (AEC)
ASPLOS 2024
Artifact Evaluation Committee (AEC)
EuroSys 2024
Artifact Evaluation Committee (AEC)
Distinguished Artifact Evaluator Award
SOSP 2023
Artifact Evaluation Committee (AEC)
MLSys 2023
Artifact Evaluation Committee (AEC)
EuroSys 2023
Artifact Evaluation Committee (AEC)
Distinguished Artifact Evaluator Award

© 2026 Konstantinos Papaioannou